CN110753517A - Ultrasound scanning based on probability mapping - Google Patents

Abstract

A system may include a probe configured to transmit an ultrasound signal to a target of interest and to receive echo information associated with the transmitted ultrasound signal. The system may also include at least one processing device configured to process the received echo information using a machine learning algorithm to generate probability information associated with the object of interest. The at least one processing device may further classify the probability information and output image information corresponding to the object of interest based on the classified probability information.

Description

Probabilistic Mapping-Based Ultrasound Scanning

Related applications

This application claims priority under 35 U.S.C § 119 based on US Provisional Application 62/504,709, filed May 11, 2017, the contents of which are incorporated herein by reference in their entirety.

Background technique

Ultrasound scanners are often used to identify target organs or other structures within the body and/or to determine characteristics associated with the target organ/structure, such as the size of the organ/structure or the volume of fluid in the organ. For example, ultrasound scanners are used to identify a patient's bladder and estimate the volume of fluid in the bladder. Typically, an ultrasound scanner is placed on a patient and triggered to generate an ultrasound signal that includes sound waves output at a specific frequency. The scanner can receive echoes from the ultrasound signal and analyze them to determine the volume of fluid in the bladder. For example, the received echoes can be used to generate corresponding images, and the corresponding images can be analyzed to detect the boundaries of the target organ, such as the bladder wall. The bladder volume can then be estimated based on the detected boundary information. However, typical ultrasound scanners often suffer from inaccuracies caused by a number of factors, for example, variability in the size and/or shape of the target organ of interest between patients, obstacles in the body that make it difficult to accurately detect the target organ/ features such as the boundaries of the structure.

Description of drawings

FIG. 1A shows an exemplary configuration of a scanning system according to an exemplary embodiment;

FIG. 1B illustrates the operation of the scanning system of FIG. 1A with respect to detecting organs in a patient;

FIG. 2 shows an exemplary configuration of logic elements included in the scanning system of FIG. 1A;

Figure 3 shows a portion of the data acquisition unit of Figure 2 in an exemplary embodiment;

Figure 4 illustrates a portion of the autoencoder unit of Figure 2 in an exemplary embodiment;

FIG. 5 illustrates an exemplary configuration of components included in one or more of the elements of FIG. 2;

FIG. 6 is a flowchart illustrating the processing performed by the various components shown in FIG. 2 according to an exemplary embodiment;

Figure 7 illustrates the output generated by the autoencoder of Figure 2 in an exemplary embodiment;

Figure 8 shows a binarization process according to the process of Figure 6;

Figure 9 is a flow chart associated with displaying information via the base unit of Figure 1A; and

FIG. 10 shows exemplary image data output by the base unit according to the process of FIG. 9 .

Detailed ways

The following detailed description refers to the accompanying drawings. The same reference numbers in different drawings may identify the same or similar elements. In addition, the following detailed description does not limit the invention.

Embodiments described herein relate to the use of machine learning, including the use of neural networks and deep learning, to identify organs or structures of interest in a patient based on information obtained via an ultrasound scanner. For example, a scanner may be used to transmit multiple ultrasound signals to a target organ, and machine learning techniques/algorithms may be used to process echo information associated with the transmitted signals. A machine learning process can be used to identify objects of interest and generate probability information associated with each portion or pixel of an image generated based on the received ultrasound echo data.

For example, in one embodiment, ultrasound echo data (eg, B-mode echo data associated with ultrasound signals transmitted on multiple different scan planes directed toward the target organ) may be used for each B-mode image Generate a probability map. In one embodiment, each pixel in the B-mode image may be mapped to a probability indicating whether that particular pixel is within or part of the target organ/structure. The results of the pixel-by-pixel analysis are used to generate a target probability map. Binarization and post-processing can then be performed to remove noise and provide a more accurate representation of the organ than conventional scanners that attempt to determine the bounding walls of the target organ and estimate dimensions based on the bounding information. In some embodiments, the output from the post-processing is displayed to medical personnel and can aid in easily locating organs when performing ultrasound scans. Other post-processing can also be performed to estimate the volume of the target organ, such as the volume of fluid in the patient's bladder.

FIG. 1A is a diagram illustrating a scanning system 100 according to an exemplary embodiment. Referring to FIG. 1 , a scanning system 100 includes a probe 110 , a base (base) unit 120 and a cable 130 .

Probe 110 includes handle portion 112 (also referred to as handle 112), trigger 114, and nose 116 (also referred to as dome or dome portion 116). The medical practitioner may hold probe 110 by handle 112 and depress trigger 114 to activate (activate) one or more ultrasound transceivers and transducers located in nose 116 to transmit to the target organ of interest Ultrasound signal. For example, Figure IB shows probe 110 positioned over the pelvic region of patient 150 and over the target organ of interest (in this example, the patient's bladder 152).

The handle 112 allows the user to move the probe 110 relative to the patient 150 . As described above, when the selected anatomical portion is scanned, the trigger 114 initiates an ultrasound scan of the selected anatomical portion when the dome 116 is in contact with the surface portion of the patient 150 . The dome 116 is typically formed from a material that provides suitable acoustic impedance matching to the anatomical portion and/or allows the ultrasound energy to be properly focused as it is projected into the anatomical portion. For example, the acoustic gel or gel pad shown at area 154 in FIG. 1B may be applied to the skin of the patient 150 over the region of interest (ROI) to provide when the dome 116 is placed on the skin of the patient 150 Acoustic impedance matching.

The dome 116 includes one or more ultrasonic transceiver elements and one or more transducer elements (not shown in FIG. 1A or FIG. 1B ). The transceiver elements transmit ultrasonic energy outward from the dome 116 and receive acoustic reflections or echoes generated by internal structures/tissues within the anatomical portion. The one or more ultrasonic transducer elements may include a one-dimensional or two-dimensional array of piezoelectric elements that can be moved within the dome 116 by a motor to target signals performed by the transceiver elements. The emission of ultrasound signals provides different scanning directions. Alternatively, the transducer elements can be fixed relative to the probe 110 so that selected anatomical regions can be scanned by selectively energizing elements in the array.

In some embodiments, probe 110 may include a directional indicator panel (not shown in FIG. 1A ) that includes a directional indicator panel that may be illuminated for initial targeting and guiding the user to approach the target organ within the ROI or multiple arrows of a structure. For example, in some embodiments, the directional arrows may not be lit if the organ or structure is centered relative to where the probe 110 is placed against the skin surface at the first location on the patient 150 . However, if the organ is off-center, an arrow or set of arrows may be illuminated to guide the user to reposition probe 110 at a second or subsequent skin location on patient 150 . In other embodiments, a direction indicator may be presented on the display 122 of the base unit 120 .

One or more transceivers located in probe 110 may include an inertial reference unit including accelerometers and/or gyroscopes preferably positioned within dome 116 or nearby. The accelerometer may be operable to sense the acceleration of the transceiver (preferably relative to a coordinate system), and the gyroscope may be operable to sense the angular velocity of the transceiver relative to the same or another coordinate system . Thus, the gyroscope may be in a conventional configuration employing dynamic elements, or the gyroscope may be an optoelectronic device, such as an optical ring gyroscope. In one embodiment, the accelerometers and gyroscopes may comprise common packaged devices and/or solid state devices. In other embodiments, the accelerometers and/or gyroscopes may comprise commonly packaged microelectromechanical systems (MEMS) devices. In each case, the accelerometer and gyroscope together allow the determination of position and/or angular changes relative to known locations in the vicinity of the anatomical region of interest within the patient.

Probe 110 may communicate with base unit 120 via a wired connection, such as cable 130 . In other embodiments, probe 110 may communicate with base unit 120 via a wireless connection (eg, Bluetooth, WiFi, etc.). In each case, the base unit 120 includes a display 122 to allow the user to view processing results from the ultrasound scan and/or to allow operational interaction with the user during operation of the probe 110 . For example, display 122 may include an output display/screen, such as a liquid crystal display (LCD), light emitting diode (LED) based display, or other type of display that provides text and/or image data to a user. For example, display 122 may provide instructions for positioning probe 110 relative to selected anatomical portions of patient 150 . Display 122 may also display two-dimensional or three-dimensional images of selected anatomical regions.

In some embodiments, the display 122 may include a graphical user interface (GUI) that allows the user to select various features associated with the ultrasound scan. For example, display 122 may allow the user to select whether patient 150 is male, female, or child. This allows the system 100 to automatically adjust the transmission, reception, and processing of ultrasound signals to suit the anatomy of a selected patient, eg, adjust the system 100 to suit various anatomical details of male and female patients. For example, when a male patient is selected via the GUI on the display 122, the system 100 may be configured to locate a single cavity (eg, a bladder) within the male patient. Conversely, when a female patient is selected via the GUI, the system 100 may be configured to image anatomical parts with multiple cavities (eg, regions of the body including the bladder and uterus). Similarly, when a pediatric patient is selected, the system 100 may be configured to adjust the emission based on the smaller size of the pediatric patient. In alternative embodiments, the system 100 may include a cavity selector configured to select a single cavity scan mode or a multiple cavity scan mode that may be used for male and/or female patients. The cavity selector may thus allow imaging of single cavity regions, or imaging of multiple cavity regions (eg, regions including the aorta and the heart). Additionally, as described below, the selection of patient type (eg, male, female, child) can be used when analyzing images to help provide an accurate representation of the target organ.

To scan a selected portion of the patient's anatomy, the dome 116 may be positioned as shown in Figure IB against a surface portion of the patient 150 proximate the portion of the anatomy to be scanned. The user activates the transceiver by pressing trigger 114 . In response, the transducer element optionally positions the transceiver, which transmits an ultrasound signal into the body, and receives a corresponding echo signal, which can be processed at least in part by the transceiver to generate the said Ultrasound images of selected anatomical sections. In a particular embodiment, the system 100 transmits ultrasound signals in a range extending from about two megahertz (MHz) to about 10 or more MHz (eg, 18 MHz).

In one embodiment, the probe 110 may be coupled to a base unit 120 configured to generate ultrasonic energy at a predetermined frequency and/or pulse repetition rate and transmit the ultrasonic energy to the transceiver. The base unit 120 also includes one or more processors or processing logic configured to process reflected ultrasound energy received by the transceiver to generate an image of the scanned anatomical region.

In yet another particular embodiment, probe 110 may be a stand-alone device that includes a microprocessor located within probe 110 and software associated with the microprocessor to operatively control the transceiver and process reflections ultrasound energy to generate ultrasound images. Accordingly, the display on probe 110 may be used to display the generated images and/or view other information associated with the operation of the transceiver. For example, the information may include alphanumeric data indicating the preferred location of the transceiver prior to performing a series of scans. In other embodiments, the transceiver may be coupled to a general-purpose computer (eg, a laptop or desktop computer) that includes software that controls, at least in part, the operation of the transceiver, and also includes software for processing transmissions from the transceiver. software to make it possible to generate images of scanned anatomical regions.

FIG. 2 is a block diagram of functional logic components implemented in system 100 according to an exemplary embodiment. Referring to FIG. 2 , the system 100 includes a data acquisition unit 210 , a convolutional neural network (CNN) autoencoder unit 220 , a post-processing unit 230 , targeting logic 240 and volume estimation logic 250 . In an exemplary embodiment, probe 110 may include data acquisition unit 210 and other functional units (eg, CNN autoencoder unit 220 , post-processing unit 230 , targeting logic 240 and volume estimation logic 250 ) may be implemented in base unit 120 . realized in. In other embodiments, certain units and/or logic may be implemented by other means, such as via a computing device or server external to both probe 110 and base unit 120 (eg, may be connected to the Internet or a local area network within a hospital). A computing device or server accessed by a wireless connection, etc.) implements specific elements and/or logic. For example, probe 110 may transmit echo data and/or image data to a processing system located remotely from probe 110 and base unit 120 via, for example, a wireless connection (eg, WiFi or some other wireless protocol/technology).

As discussed above, probe 110 may include a transceiver that generates ultrasound signals, receives echoes from the transmitted signals, and generates B-modes based on the received echoes (eg, the size or strength of the received echoes) image data. In an exemplary embodiment, data acquisition unit 210 acquires data associated with a plurality of scan planes corresponding to regions of interest within patient 150 . For example, probe 110 may receive echo data processed by data acquisition unit 210 to generate two-dimensional (2D) B-mode image data to determine the size and/or volume of the bladder. In other embodiments, the probe 110 can receive echo data that is processed to generate three-dimensional (3D) image data that can be used to determine the size and/or volume of the bladder.

For example, FIG. 3 shows an exemplary data acquisition unit 210 for acquiring 3D image data. Referring to FIG. 3 , the data acquisition unit 210 includes a transducer 310 , an outer surface 320 of the dome portion 116 and a base 360 . The elements shown in FIG. 3 may be included within the dome portion 116 of the probe 110 .

Transducer 310 may transmit ultrasonic signals from probe 110, as shown at 330 in FIG. 3 . The transducer 310 may be mounted to allow the transducer 310 to rotate about two vertical axes. For example, the transducer 310 may rotate relative to the base 360 about a first axis 340 and relative to the base 360 about a second axis 350 . The first axis 340 is referred to herein as the theta axis and the second axis 350 is referred to herein as the phi axis. In an exemplary embodiment, theta and phi ranges of motion may be less than 180 degrees. In one embodiment, interlacing may be performed with respect to theta motion and phi motion. For example, the transducer 310 may move in the theta direction and then move in the phi direction. This enables the data acquisition unit 210 to obtain smooth and continuous volume scans and increases the rate at which scan data is acquired.

In an exemplary embodiment, the data acquisition unit 210 may resize (size) the B-mode image before forwarding the B-mode image to the CNN auto-encoder unit 220 . For example, the data acquisition unit 210 may include logic to reduce the size of the B-mode image through a reduction or decimation process. The reduced size B-mode image may then be input to the CNN auto-encoder unit 220, which will generate an output probability map, as described in more detail below. In alternative embodiments, the CNN auto-encoder unit 220 may reduce or decimate the input B-mode image itself at the input layer. In either case, reducing the size/amount of B-mode image data may reduce the processing time and processing power required by the CNN autoencoder unit 220 to process the B-mode image data. In other embodiments, the data acquisition unit 210 may not perform resizing before inputting the B-mode image data to the CNN auto-encoder unit 220 . In other embodiments, the data acquisition unit 210 and/or the CNN auto-encoder unit 220 may perform image enhancement operations such as brightness normalization, contrast enhancement, scan conversion, etc., to improve accuracy with respect to generating output data.

Referring again to FIG. 2 , the CNN autoencoder unit 220 may include logic for processing data received via the data acquisition unit 210 . In an exemplary embodiment, the CNN autoencoder unit 220 may perform deep neural network (DNN) processing including multiple convolutional layer processing and multiple kernels for each layer. or filter, as described in more detail below. The terms "CNN auto-encoder unit" or "auto-encoder unit" as used herein should be interpreted broadly to include neural networks and/or machine learning systems/units, in contrast to classifiers that output global labels without spatial information, where both input and output have spatial information.

For example, the CNN auto-encoder unit 220 includes logic to map received image inputs to outputs with the smallest possible amount of distortion. CNN processing can be similar to other types of neural network processing, but CNN processing uses explicit assumptions (i.e. the input is an image), which makes it easier for CNN processing to encode various properties/restrictions into said processing, reducing The amount of parameters that must be processed or factored by the CNN autoencoder unit 220. In an exemplary embodiment, the CNN auto-encoder unit 220 performs a convolution process to generate feature maps associated with the input images. The feature map can then be sampled multiple times to generate the output. In an exemplary embodiment, the kernel size of the CNN used by the CNN auto-encoder unit 220 may have a size of 17x17 or less to provide sufficient speed to generate the output. Additionally, the 17x17 kernel size allows the CNN auto-encoder unit 220 to capture sufficient information around points of interest within the B-mode image data. Additionally, according to an exemplary embodiment, the number of convolutional layers may be eight or less, with each layer having five or less kernels. However, it should be understood that smaller kernel sizes (eg, 3x3, 7x7, 9x9, etc.) or larger kernel sizes (eg, greater than 17x17), additional kernels per layer (eg, greater than five), and Additional convolutional layers (eg, more than ten and up to hundreds).

In typical applications involving CNN processing, the data dimension (size) is reduced by adding a narrow bottleneck layer within the process so that only data of interest can pass through the narrow layer. This reduction in data dimensionality is typically achieved by adding a "pooling" layer or using a larger "stride" to reduce the size of the image processed by the neural network. However, in some embodiments described herein for bladder detection where the spatial accuracy of the detected bladder wall position is important for accurate volume calculations, pooling and/or large step sizes are minimized using or Combined with other spatial resolution preserving techniques such as residual connections or dilated convolutions.

Although the exemplary system 100 depicts processing B-mode input data using the CNN autoencoder unit 220, in other embodiments, the system 100 may include other types of autoencoder units or machine learning units. For example, the CNN auto-encoder unit 220 may include a neural network structure in which the output layer has the same number of nodes as the input layer. In other embodiments, other types of machine learning modules or units may be used, where the size of the input layer is not equal to the size of the output layer. For example, a machine learning module can generate (in terms of layers) a probability map output that is larger than twice the input image or smaller than half the input image. In other embodiments, the machine learning unit included in the system 100 may use various machine learning techniques and algorithms, such as decision trees, support vector machines, Bayesian networks, and the like. In each case, the system 100 uses machine learning algorithms to generate probabilistic information about the B-mode input data, which in turn can be used to estimate the volume of the target organ of interest, as described in detail below.

Figure 4 schematically shows a portion of a CNN auto-encoder unit 220 according to an exemplary embodiment. 4 , the CNN autoencoder unit 220 may include a spatial input 410 , an FFT input 420 , a query 422 , a feature map 430 , a feature map 440 , a query 442 , a kernel 450 , a bias 452 , a kernel 460 , and a bias 462 . Input space 410 may represent 2D B-mode image data provided by data acquisition unit 210 . The CNN autoencoder 220 may perform a Fast Fourier Transform (FFT) to convert the image data to the frequency domain and apply filters or weights to the input FFT via the kernel FFT 450. The output of the convolution process may be biased via bias value 452 and an Inverse Fast Fourier Transform (IFFT) function applied, the result of which is passed to look-up table 422 to generate spatial feature map 430 . CNN autoencoder unit 220 may apply FFT to spatial feature map 430 to generate FFT feature map 440, and this process may be repeated for additional convolutions and kernels. For example, if the CNN autoencoder unit 220 includes eight convolutional layers, the process may continue seven more times. Additionally, the kernels applied to each subsequent feature map correspond to the number of kernels multiplied by the number of feature maps, as shown by four kernels 460 in FIG. 4 . Bias 452 and 462 can also be applied to improve the performance of CNN processing.

As described above, the CNN auto-encoder unit 220 may perform convolution in the frequency domain using FFT. This approach allows the system 100 to use less computing power to implement the CNN algorithm compared to larger systems that can use multiple computers to execute the CNN algorithm. In this manner, the system 100 can use the handheld unit and base station (eg, probe 110 and base unit 120) to perform CNN processing. In other embodiments, spatial domain methods may be used. The system 100 is capable of working with other processing devices (eg, via a network (eg, a wireless or wired network) connected to the processing device of the system 100 and/or via a client/server approach (eg, the system 100 is a client) with the system 100 The spatial domain approach may use additional processing power in the case of communication with the operating processing device.

The output of the CNN autoencoder unit 220 is probability information associated with the probability that each processed portion or pixel of the processed input image is within the target organ of interest. For example, the CNN auto-encoder unit 220 may generate a probability map in which each pixel associated with the input image data being processed is mapped to a probability corresponding to a value between 0 and 1, where a value of zero indicates that the pixel is in The probability within the target organ is 0%, and a value of 1 indicates that the pixel is within the target organ with a probability of 100%, as described in more detail below. The CNN auto-encoder unit 220 performs pixel analysis or spatial location analysis on the processed image rather than the input image. As a result, pixel-by-pixel analysis of the processed image may not correspond one-to-one with the input image. For example, based on the resizing of the input image, one processed pixel or spatial location analyzed by the CNN autoencoder unit 220 to generate probability information may correspond to multiple pixels in the input image, and vice versa. Additionally, the term "probability" as used herein should be interpreted broadly to include the likelihood that a pixel or portion of an image is within a target or organ of interest. The term "probability information" as used herein should also be construed broadly to include discrete values, such as binary or other values.

In other embodiments, the CNN auto-encoder unit 220 can generate a probability map in which each pixel is mapped to a value that can be correlated with a probability value or indicator (eg, a value ranging from -10 to 10, A value corresponding to one of the 256 grayscale values, etc.) associated with various values. In each case, the values or units generated by the CNN autoencoder unit 220 may be used to determine the probability that a pixel or portion of the image is within the target organ. For example, in the 256 grayscale example, a value of 1 may represent a 0% probability that a pixel or portion of the image is within the target organ, while a value of 256 may represent a 100% probability that the pixel or image is within the target organ.

In other embodiments, the CNN autoencoder unit 220 may generate discrete output values, such as binary values, that indicate whether a pixel or output region is within the target organ. For example, the CNN auto-encoder unit 220 may include a binarization or classification process that generates discrete values, eg, "1" when the pixel is within the target organ and "1" when the pixel is not within the target organ is "0". In other cases, the resulting value may not be binary, but may be related to whether the pixel is inside or outside the target organ.

In some embodiments, the CNN autoencoder unit 220 may consider various factors when analyzing pixel-by-pixel data. For example, the CNN auto-encoder unit 220 may receive input from the user via a GUI displayed on the display 122 of the base unit 120 (FIG. 1A) indicating whether the patient 150 is male, female, or child, and based on stored data with the particular type Information about the possible size, shape, volume, etc. of the patient's target organ is used to adjust the probability value. In such an embodiment, the CNN auto-encoder unit 220 may include three different CNNs trained with male, female, and child data, and the CNN auto-encoder unit 220 may use the appropriate CNN based on the selection.

In some embodiments, the CNN autoencoder unit 220 may use, for example, B-mode image data associated with the subject to automatically identify the subject's patient demographic information, such as gender, age, age range, adult or child status Wait. The CNN autoencoder unit 220 may also automatically identify the clinical condition of the subject using, for example, B-mode image data (eg, body mass index (BMI), body size and/or weight, etc.). The CNN autoencoder unit 220 may also automatically identify device information, such as position information of the probe 110, aiming quality of the probe 110 relative to the target of interest, etc., when the system 100 scans.

In other embodiments, another processing device (eg, a processing device similar to autoencoder unit 220 and/or processor 520 ) may use, for example, another neural network or other processing logic to perform analysis of patient demographics, clinical Automatic detection of condition and/or device information, and the automatically determined output may be provided as input to the CNN autoencoder unit 220. Furthermore, in other embodiments, patient demographic information, clinical condition and/or device information, patient data, etc. may be manually entered via, eg, display 122 of base unit 120 or via input selections on probe 110 . In each case, information automatically identified by the CNN auto-encoder unit 220 or manually input to the CNN auto-encoder unit 220/system 100 may be used to select an appropriate CNN to process the image data.

In other embodiments, other information may be utilized to train the CNN auto-encoder unit 220. For example, the CNN autoencoder unit 220 may be trained with patient data associated with the subject, which may include information obtained using the patient's medical history data and via a physical examination of the patient prior to scanning the object of interest information obtained. For example, patient data may include patient medical history information, such as patient surgical history, chronic disease history (eg, bladder disease information), previous images of objects of interest (eg, previous images of the subject's bladder), etc. Data obtained from a physical examination performed by the subject, such as pregnancy status, presence of scar tissue, hydration problems, abnormalities in the target area (such as abdominal distention or swelling), etc. In an exemplary embodiment, patient data may be entered into the system 100 via the display 122 of the base unit 120 . In each case, information automatically generated by the CNN autoencoder unit 220 and/or another processing device and/or manually entered into the system 100 may be provided as input to the machine learning process performed by the system 100 to help improve The accuracy of the data associated with the object of interest generated by the system 100 .

In other cases, the autoencoder unit 220 may receive information via a GUI provided on the display 122 with the type of organ being imaged (eg, bladder, aorta, prostate, heart, kidney, uterus, blood vessels, amniotic fluid, fetus, etc. ) and the number of organs, etc., and use an appropriate CNN trained on the selected organs.

Post-processing unit 230 includes logic for receiving pixel-by-pixel probability information and applying a "smart" binarization probability algorithm. For example, post-processing unit 230 may perform interpolation to more clearly define contour details, as described in detail below. Additionally, the post-processing unit 230 may adjust the output of the CNN auto-encoder unit 220 based on the subject type. For example, if "Children" was selected through the GUI on display 122 prior to initiating an ultrasound scan using probe 110, post-processing unit 230 may ignore data from CNN auto-encoder unit 220 corresponding to locations deeper than a certain depth output, as the depth of the bladder in a child is often shallow due to the short stature of the typical child. As another example, the post-processing unit 230 may determine whether to select a single primary region or multiple regions of interest based on the organ type. For example, if the type of organ being scanned is the bladder, the post-processing unit 230 may select a single primary region since there is only one bladder in the body. However, if the target is the pubic bone, the post-processing unit 230 may select up to two regions of interest, which correspond to both sides of the pubic bone.

Targeting logic 240 includes logic for determining whether the target organ is properly centered relative to probe 110 during the ultrasound scan. In some embodiments, targeting logic 240 may generate text or graphics to guide the user in adjusting the position of probe 110 to achieve better scanning of the target organ. For example, targeting logic 240 may analyze data from probe 110 and determine that probe 110 needs to be moved to the left side of patient 150 . In this case, targeting logic 240 may output text and/or graphics (eg, blinking arrows) to display 122 to guide the user to move probe 110 in the appropriate direction.

Volume estimation logic 250 may include logic for estimating the volume of the target organ. For example, the volume estimation logic 250 may estimate the volume based on the 2D images generated by the post-processing unit 230, as described in detail below. Where a 3D image is provided, the volume estimation logic 250 may simply use the 3D image to determine the volume of the target organ. Volume estimation logic 250 may output the estimated volume via display 122 and/or a display on probe 110 .

For simplicity, the exemplary configuration shown in Figure 2 is provided. It should be understood that the system 100 may include more or fewer logical units/devices than those shown in FIG. 2 . For example, system 100 may include multiple data acquisition units 210 and multiple processing units that process received data. Additionally, the system 100 may include additional elements such as a communication interface (eg, a radio frequency transceiver) to transmit and receive information via an external network to aid in analyzing the ultrasound signal to identify a target organ of interest.

Additionally, various functions performed by specific components in system 100 will be described below. In other embodiments, various functions described as being performed by one apparatus may be performed by another apparatus or apparatuses, and/or various functions described as being performed by multiple apparatuses may be combined and performed by a single apparatus device executes. For example, in one embodiment, the CNN auto-encoder unit 220 may convert the input image to probability information, generate intermediate map outputs (as described below), and may also convert the intermediate outputs to, for example, volume information, length information, area information Wait. That is, a single neural network processing device/unit may receive input image data and output processed image output data and volume and/or size information. In this example, a separate post-processing unit 230 and/or volume estimation logic 250 may not be required. Additionally, in this example, any intermediate map output may be accessible or visible or inaccessible or invisible to an operator of the system 100 (eg, the intermediate map may not be directly accessible to the user) /visible part of internal processing). That is, a neural network (eg, CNN auto-encoder unit 220) included in system 100 can convert received ultrasound echo information and/or images and output volume information or other dimensional information of the object of interest, while No additional input by the user of the system 100 or only a small amount of additional input is required.

FIG. 5 shows an exemplary configuration of apparatus 500 . Apparatus 500 may correspond to components of, for example, CNN autoencoder unit 220 , post-processing unit 230 , targeting logic 240 and volume estimation logic 250 . Referring to FIG. 5 , the apparatus 500 may include a bus 510 , a processor 520 , a memory 530 , an input device 540 , an output device 550 and a communication interface 560 . The bus 510 may include paths that allow communication between the various elements of the apparatus 500 . In an exemplary embodiment, all or some of the components shown in FIG. 5 may be implemented and/or controlled by processor 520 executing software instructions stored in memory 530 .

Processor 520 may include one or more processors, microprocessors, or processing logic that can interpret and execute instructions. Memory 530 may include random access memory (RAM) or another type of dynamic storage device that may store information and instructions for execution by processor 520 . Memory 530 may also include read only memory (ROM) devices or another type of static storage device that may store static information and instructions for use by processor 520 . The memory 530 may further include a solid state drive (SDD). Memory 530 may also include magnetic and/or optical recording media (eg, hard disks) and their corresponding drives.

Input device 540 may include a mechanism (mechanism) that allows a user to enter information into device 500, such as a keyboard, keypad, mouse, pen, microphone, touch screen, voice recognition and/or biometric mechanisms, and the like. Output device 550 may include a mechanism for outputting information to a user, including a display (eg, a liquid crystal display (LCD)), a printer, a speaker, and the like. In some embodiments, a touch screen display can be used as an input device and an output device.

Communication interface 560 may include one or more transceivers that device 500 uses to communicate with other devices via wired, wireless, or optical mechanisms. For example, communication interface 560 may include one or more radio frequency (RF) transmitters, receivers and/or transceivers and one or more antennas for transmitting and receiving RF data via a network. Communication interface 560 may also include a modem or Ethernet interface to the LAN or other mechanism for communicating with elements in the network.

For simplicity, the exemplary configuration shown in Figure 5 is provided. It should be understood that apparatus 500 may include more or fewer apparatuses than those shown in FIG. 5 . In an exemplary embodiment, apparatus 500 performs operations in response to processor 520 executing sequences of instructions contained in a computer-readable medium (eg, memory 530). Computer readable media can be defined as physical or logical storage devices. The software instructions may be read into memory 530 from another computer-readable medium (eg, a hard disk drive (HDD), SSD, etc.) or from another device via communication interface 560 . Alternatively, hardware-connected circuits such as Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), etc. may be used in place of or in combination with software instructions to implement processes (processes) according to the embodiments described herein. ). Accordingly, the embodiments described herein are not limited to any specific combination of hardware circuitry and software.

6 is a flowchart illustrating an example process associated with identifying an object of interest and identifying a parameter (eg, volume) associated with the object of interest. Processing may begin with the user operating probe 110 to scan the target organ of interest. In this example, the target organ is assumed to be the bladder. It should be understood that the features described herein can be used to identify other organs or structures in the body.

In an exemplary embodiment, a user may depress trigger 114 and a transceiver included in probe 110 transmits ultrasonic signals and acquires B-mode data associated with echo signals received by probe 110 (square). block 610). In one embodiment, the data acquisition unit 210 may transmit ultrasound signals in 12 different planes through the bladder and generate 12 B-mode images corresponding to the 12 different planes. In this embodiment, the data may correspond to 2D image data. In other embodiments, the data acquisition unit 210 may generate 3D image data. For example, as discussed above with respect to FIG. 3, data acquisition unit 210 may perform interlacing to generate a 3D image. In each case, the number of transmitted ultrasound signals/scan planes may vary based on the particular implementation. As described above, in some embodiments, the data acquisition unit 210 may reduce the size of the B-mode image before forwarding the B-mode data to the CNN autoencoder unit 220. For example, the data acquisition unit 210 may reduce the size of the B-mode image by 10% or more.

In each case, it is assumed that the CNN autoencoder unit 220 receives 2D B-mode data and processes the data to remove noise from the received data. For example, referring to FIG. 7, the CNN autoencoder unit 220 may receive B-mode image data 710, where dark areas or dark areas 712 correspond to the bladder. As shown, the B-mode image data includes areas that are irregular or that may appear unclear or blurred to a user. For example, region 712 in FIG. 7 includes a brighter area around the bladder and an indistinct border. Such noisy areas can make it difficult to accurately estimate bladder volume.

In this case, the CNN autoencoder unit 220 performs denoising on the acquired B-mode image 710 by generating a target probability map (block 620). For example, as described above, the CNN autoencoder 220 may utilize CNN techniques to generate probability information associated with each pixel in the input image.

The base unit 120 may then determine whether the entire cone data (ie, all scan plane data) has been acquired and processed (block 630). For example, the base unit 120 may determine whether all 12 B-mode images corresponding to 12 different scans through the bladder have been processed. If all B-mode image data has not been processed (block 630-NO), the base unit 120 controls to move to the next scan plane position (block 640), and processing proceeds to block 610 to process another Scan plane associated B-mode image.

If all of the B-mode image data has been processed (block 630-Yes), the base unit 120 may use the 3D information to modify the probability map (block 650). For example, the CNN auto-encoder unit 220 may modify some of the probabilistic information generated by the CNN auto-encoder unit 220 using stored hypothesis information related to the 3D shape and size of the bladder based on whether the patient is male, female, child, etc., effectively Modify the size and/or shape of the bladder. That is, as described above, the CNN autoencoder unit 220 may use patient-based demographic information, the patient's clinical condition, device information associated with the system 100 (eg, probe 110 ), patient data (eg, patient data) of the patient. , patient medical history information and patient examination data), etc. For example, the CNN autoencoder unit 220 may use a CNN trained with male patient data if patient 150 is male, a CNN trained with female patient data if patient 150 is female, and a CNN trained with female patient data if patient 150 is a child Use a CNN trained on children's data, use a CNN trained on the patient's age range, use a CNN trained on the patient's medical history, etc. In other embodiments, for example, when the base unit 120 receives and processes the 3D image data, no additional processing may be performed and block 650 may be skipped. In either case, system 100 may display P-mode image data (block 660 ), such as image 720 shown in FIG. 7 .

In either case, the base unit 120 may segment the target region through a binarization process using the probability map (block 670). For example, post-processing unit 230 may receive the output of CNN auto-encoder unit 220 and adjust the size (size) of the probability map (eg, by interpolation), smooth the probability map, and/or (eg, by filtering) the probability map to denoise. For example, in one embodiment, the probability map may be resized to a larger size by interpolation to obtain better resolution and/or to at least partially restore the spatial resolution of the original B-mode image data that may have been reduced in size Rate. In one embodiment, 2D Lanczos differencing may be performed to resize the image associated with the target probability map.

In addition, the base unit 120 may perform classification or binarization processing to convert the probability information from the probability mapping unit into binarized output data. For example, the post-processing unit 230 may convert the probability values to binary values. When multiple candidate probability values are identified for a particular pixel, the post-processing unit 230 may select the most salient value. In this way, when multiple candidate values are identified, the post-processing unit 230 may apply some "intelligence" to select the most probable value.

Figure 8 schematically illustrates an exemplary smart binarization process. Referring to Figure 8, image 810 shows the output from a probability map or pixel classification corresponding to a 2D ultrasound image, wherein the probability information is converted into a grayscale image with various intensities. As shown, image 810 includes a gray area labeled 812 and a gray area labeled 814 that represent possible locations of portions of the bladder. Post-processing unit 230 identifies peaks or cusps within image 810 that have the greatest intensity, as indicated by crosshairs 822 shown in image 820 . The post-processing unit 230 may then fill in the area around the peak point for the area whose intensity is greater than the threshold intensity, as shown by the area 832 in the image 830 . In this case, regions within region 820 whose threshold intensity values are less than the threshold intensity are not filled, resulting in the gray area 814 displayed in image 810 being removed. Post-processing unit 230 may then fill in the background, as shown by area 842 in image 840 . Post-processing unit 230 then fills in any holes or open areas within the image, as shown by area 852 in image 850 . Apertures in region 842 may correspond to noise regions or regions associated with certain obstructions in patient 150 . In this way, the post-processing unit 230 identifies the most likely location and size of the bladder. That is, region 852 is considered to be a portion of patient 150's bladder.

In other embodiments, post-processing unit 230 may use information within image 810 other than peak intensity values. For example, the post-processing unit 230 may use the processed probability peaks (eg, smoothed probability map peaks), use multiple peaks to identify multiple fill regions, and the like. As other examples, the post-processing unit 230 may select a "primary" region based on the area in each region, the peak probability, or the average probability. In other embodiments, post-processing unit 230 may use one or more seed points manually entered by an operator via, for example, display 122, use an algorithm that generates one or more seed points, perform another type of seed point that does not use seed points Thresholding etc. to identify areas of the patient's bladder.

After processing image 810 in this manner, base unit 120 may output an image, such as image 720 shown in FIG. 7 . Referring to Figure 7, image 720 includes a region 722 corresponding to the bladder. As shown, the edges of bladder 722 are much more defined than the boundaries in image 712, providing a more accurate representation of the bladder. In this way, the base unit 120 can use the luminance value of each pixel and the local gradient values of neighboring pixels and statistical methods such as hidden Markov models and neural network algorithms (eg, CNN) to generate B. Probability values for each pixel in the mode image and denoising the B-mode data.

The base unit 120 may then convert the segmentation result to a target volume (block 670). For example, the post-processing unit 230 may sum the volumes of all voxels in the 3D space corresponding to each valid target pixel in the binarization map. That is, the volume estimation logic 250 may sum the voxels in the 12 segmented target images to estimate the volume of the bladder. For example, the contribution or volume of each voxel may be pre-computed and stored in a look-up table within the base unit 120. In this case, the volume estimation logic 250 may use the sum of the voxels as an index to the lookup table to determine the estimated volume. The volume estimation logic 250 may also display the volume via the display 122 of the base unit 120 . For example, the volume estimation logic 250 may display the estimated volume of the bladder (ie, 135 milliliters (mL) in this example) at area 724 in FIG. 7 , which is output to the display 122 of the base unit 120 . Alternatively, volume estimation logic 250 may display volume information via a display on probe 110 . The post-processing unit 230 may also display the segmentation results (block 690). That is, the post-processing unit 230 may display the 12 segments of the bladder via the display 122 of the base unit 120 .

In some implementations, the system 100 may not perform a binarization process on the probability map information. For example, in some embodiments, CNN auto-encoder unit 220 and/or post-processing unit 230 may apply a look-up table to the probabilistic mapping information to identify possible portions of the target organ of interest, and display the output via display 122 .

Referring back to block 620, in some embodiments, the probability mapping unit 230 may display the information in real-time as the information is generated. FIG. 9 illustrates an example process associated with providing additional display information to a user. For example, post-processing unit 230 may display probabilistic pattern information (referred to herein as P-modes) in real-time via display 122 as the probabilistic pattern information is generated (FIG. 9, block 910). The post-processing unit 230 may also segment the object (block 920) and display the segmentation results using the B-mode image (block 930). For example, FIG. 10 shows three B-mode images 1010 , 1012 and 1014 and corresponding P-mode images 1020 , 1022 and 1024 . In other embodiments, all 12 B-mode images and 12 corresponding P-mode images may be displayed. As shown, P-mode images 1020 , 1022 and 1024 are much sharper than B-mode images 1010 , 1012 and 1014 . Additionally, in some embodiments, the post-processing unit 230 may provide an outline of the bladder boundary displayed in each P-mode image. For example, as shown in FIG. 10, each of the P-mode images 1020, 1022, and 1024 may include, for example, outlines that are a different color or brighter color than the interior portion of the bladder.

Embodiments described herein use machine learning to identify organs or structures of interest in a patient based on information obtained via an ultrasound scanner. A machine learning process may receive image data and generate probability information for each particular portion (eg, pixel) of the image to determine the probability that the particular portion is within the target organ. Post-processing analysis can also refine the probabilistic information with additional information such as the gender or age of the patient, specific target organs, etc. In some cases, the volume of the target organ may also be provided to the user along with the real-time probabilistic mode image.

The foregoing description of exemplary embodiments provides illustration and description, but is not intended to be exhaustive or to limit the embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of the embodiments.

For example, features have been described above with respect to identifying an object of interest (eg, a patient's bladder) and using CNN processing to estimate the volume of the object (eg, bladder). In other embodiments, other organs or structures can be identified, and dimensions or other parameters associated with the organs/structures can be estimated. For example, the processes described herein can be used to identify and display the prostate, kidney, uterus, ovary, aorta, heart, blood vessels, amniotic fluid, fetus, etc. as well as specific features (eg, volume and/or size-related) associated with these objects Measurements).

For example, in embodiments in which the treatments described herein are used with respect to various organs or targets other than the bladder (eg, aorta, prostate, kidney, heart, uterus, ovary, blood vessels, amniotic fluid, fetus, etc.), there may be Generates additional dimension-dependent measurements. For example, the length, height, width, depth, diameter, area, etc. of the organ or region of interest can be calculated. For example, for scans of the aorta, measuring the diameter of the aorta may be important when trying to identify abnormalities such as aneurysms. For prostate scans, it may be necessary to measure the width and height of the prostate. In these cases, measurements such as length, height, width, depth, diameter, area, etc. may be generated/estimated using the machine learning process described above. That said, the machine learning described above can be used to identify boundary walls or other items of interest, and estimate specific parameters related to size that are of concern to medical personnel.

Furthermore, features have been described above primarily with respect to using echo data to generate B-mode images and applying machine learning to B-mode images to identify volume, length, or other information associated with objects. In other embodiments, other types of ultrasound input image data may be used. For example, in other embodiments, C-mode image data may be used that typically includes a representation of an object of interest (eg, a bladder) formed in a plane oriented perpendicular to the B-mode image. Still further, in other embodiments, radio frequency (RF) or quadrature signals (eg, IQ signals) may be used as input to the CNN autoencoder unit 220 to generate probabilistic output maps associated with targets.

Furthermore, features have been described above with respect to generating a single probability map. In other embodiments, multiple probability maps may be generated. For example, the system 100 may generate one probability map for the target organ of interest (eg, bladder), another probability map for the pubis/pubic shadow, and another probability map for the prostate. In this manner, a more accurate representation of the internal organs of the patient 150 may be generated, which may enable a more accurate volume estimation of the target organ (eg, bladder).

Additionally, the features described herein relate to pixel-by-pixel analysis of B-mode image data. In other embodiments, edge mapping may be used instead of pixel-by-pixel mapping. In this embodiment, a CNN algorithm can be used to detect the edges of the object. In a further embodiment, a polygonal coordinate method can be used to identify discrete parts of the bladder and then connect the points. In this embodiment, a contour edge tracking algorithm can be used to connect the points of the target organ.

Additionally, various inputs (eg, information indicating whether the patient is male, female, child, etc.) have been described above. Other inputs to probability mapping and/or binarization may also be used. For example, a body mass index (BMI), age, or age range can be entered into the base unit 120, and the base unit 120 can automatically adjust the process based on the particular BMI, age, or age range. Other inputs to the probability mapping and/or binarization process (eg, depth per pixel, plane orientation, etc.) may be used to improve the accuracy of volume estimates and/or output images generated by system 100 .

Additionally, as discussed above, training data associated with various types of patients (males, females, and children) can be used to help generate P-mode data. For example, thousands or more images of training data can be used to generate a CNN algorithm for processing B-mode input data to identify objects of interest. Additionally, thousands or more images may be input or stored in the base unit 120 to help modify the output of the CNN autoencoder unit 220. This is especially useful where an expected obstacle (eg, the pubic bone for bladder scans) adversely affects the image. In these embodiments, the base unit 120 may store information on how to address and minimize the impact of obstacles. The CNN auto-encoder unit 220 and/or the post-processing unit 230 can then deal with obstacles more accurately.

Furthermore, the features described herein refer to the use of B-mode image data as input to the CNN auto-encoder unit 220. In other embodiments, other data may be used. For example, echo data associated with transmitted ultrasound signals may include harmonic information that may be used to detect target organs such as the bladder. In this case, higher order harmonic echo information (eg, second or higher order harmonics) related to the frequency of the transmitted ultrasound signal can be used to generate probability mapping information without generating B pattern image. In other embodiments, the P-mode image data may be enhanced using higher order harmonic information in addition to the B-mode data described above. In still further embodiments, the probe 110 may transmit ultrasound signals at multiple frequencies, and the echo information associated with the multiple frequencies may be used as input to the CNN autoencoder unit 220 or other machine learning module to Detect the target organ and estimate the volume, size and other parameters of the target organ.

For example, multiple B-mode images at the fundamental frequency and multiple B-mode images at higher-order harmonic frequencies or at multiple higher-order harmonic frequencies may be used as inputs to the CNN auto-encoder unit 220. Additionally, fundamental and harmonic frequency information can be preprocessed and used as input to the CNN auto-encoder unit 220 to help generate probabilistic maps. For example, the ratio between the harmonic power and the fundamental frequency power can be used as an input to the CNN auto-encoder unit 220 to enhance the accuracy of the probability mapping.

Additionally, in some embodiments, the post-processing described above may use a second machine learning (eg, CNN) algorithm to denoise the image data and/or perform contour/edge tracking on the image.

Furthermore, the embodiments have been described above with respect to the data acquisition unit 210 that acquires 2-dimensional (2D) B-mode image data. In other embodiments, higher dimensional image (eg, 2.5D or 3D) data may be input to the CNN autoencoder unit 220. For example, for a 2.5D implementation, the CNN autoencoder unit 220 may use B-mode images associated with several scan planes and adjacent scan planes to improve accuracy. For 3D implementations, the CNN autoencoder unit 220 may generate 12 probability maps for each of the 12 scan planes, and the post-processing unit 230 may use all 12 probability maps to generate a 3D image based on the 12 probability maps (eg via a 3D flood fill algorithm). A classification and/or binarization process can then be performed on the 2.5D or 3D image to generate, for example, a 3D output image.

Furthermore, although a series of actions have been described with respect to Figures 6 and 9, the order of the actions may differ in other implementations. Furthermore, non-dependent actions can be implemented in parallel.

It will be apparent that, in the embodiments shown in the drawings, the various features described above may be implemented in many different forms of software, firmware and hardware. The actual software code or dedicated control hardware used to implement the various features is not limiting. Thus, the operation and behavior of the features have been described without reference to the specific software code, it being understood that those of ordinary skill in the art would be able to design software and control hardware to implement the various features based on the descriptions herein.

Additionally, portions of the invention may be implemented as "logic" that performs one or more functions. The logic may include hardware (eg, one or more processors, microprocessors, application specific integrated circuits, field programmable gate arrays, or other processing logic), software, or a combination of hardware and software.

In the foregoing specification, various preferred embodiments have been described with reference to the accompanying drawings. It will, however, be evident that various modifications and changes may be made, and additional embodiments may be practiced, without departing from the broader scope of the invention as set forth in the appended claims. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense.

No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly described as such. Also, as used herein, the article "a" is intended to include one or more of the items. Furthermore, the phrase "based on" is intended to mean "based at least in part on" unless expressly stated otherwise.

Claims (21)

1. A system, comprising:

a probe configured to:

transmitting an ultrasonic signal to an object of interest, and

receiving echo information associated with the transmitted ultrasound signals; and

at least one processing device configured to:

processing the received echo information using a machine learning algorithm to generate probability information associated with the object of interest,

classifying the probability information, and

based on the classified probability information, image information corresponding to the object of interest is output.

2. The system of claim 1, wherein when classifying the probability information, the at least one processing device is configured to binarize the probability information, and the at least one processing device is further configured to:

based on the binarized probability information, at least one of a volume, length, height, width, depth, diameter, or area associated with the object of interest is estimated.

3. The system of claim 1, wherein the machine learning algorithm comprises a convolutional neural network algorithm.

4. The system of claim 1, further comprising:

a display configured to receive the image information and display the image information.

5. The system of claim 4, wherein the display is further configured to:

b-mode image data corresponding to the received echo information and output image information corresponding to the target of interest are displayed simultaneously.

6. The system of claim 1, wherein the at least one processing device is further configured to:

generating aiming instructions for directing the probe to a target of interest.

7. The system of claim 1, wherein the object of interest comprises a bladder.

8. The system of claim 1, wherein the at least one processing device is further configured to:

receiving at least one of gender information of a subject, information indicating that the subject is a child, or patient data associated with the subject, and

the received echo information is processed based on the received information.

9. The system of claim 1, wherein the at least one processing device is further configured to:

automatically determining at least one of demographic information of the subject, clinical information of the subject, or device information associated with the probe, and

the received echo information is processed based on the automatically determined information.

10. The system of claim 1, wherein, when processing the received echo information, the at least one processing device is configured to:

processing the received echo information to generate output image data,

processing pixels associated with the output image data,

the value of each pixel processed is determined,

a peak is identified, an

Filling a region around a point associated with the peak to identify a portion of the target of interest.

11. The system of claim 1, wherein, when processing the received echo information, the at least one processing device is configured to:

identifying higher order harmonic information about a frequency associated with the transmitted ultrasound signal, and

probability information is generated based on the identified higher order harmonic information.

12. The system of claim 1, wherein the probe is configured to transmit the received echo information to the at least one processing device via a wireless interface.

13. The system of claim 1, wherein the object of interest comprises one of an aorta, a prostate, a heart, a uterus, a kidney, a blood vessel, amniotic fluid, or a fetus.

14. A method, comprising:

transmitting an ultrasound signal to a target of interest via an ultrasound scanner;

receiving echo information associated with the transmitted ultrasound signals;

processing the received echo information using a machine learning algorithm to generate probability information associated with the object of interest;

classifying the probability information; and

based on the classified probability information, image information corresponding to the object of interest is output.

15. The method of claim 14, wherein classifying the probability information comprises binarizing the probability information, the method further comprising:

estimating at least one of a volume, a length, a height, a width, a depth, a diameter, or an area associated with the object of interest based on the binarized probability information; and

outputting the at least one of the volume, length, height, width, depth, diameter, or area to a display.

16. The method of claim 14, further comprising:

b-mode image data corresponding to the echo information and output image information corresponding to the target of interest are displayed simultaneously.

17. The method of claim 14, further comprising:

receiving at least one of gender information, age range information, or body mass index information; and

the received echo information is processed based on the received information.

18. A system, comprising:

a memory; and

at least one processing device configured to:

receiving image information corresponding to an object of interest,

processing the received image information using a machine learning algorithm to generate probability information associated with the object of interest,

classifying the probability information, and

based on the classified probability information, second image information corresponding to the object of interest is output.

19. The system of claim 18, wherein the at least one processing device is further configured to:

based on the classified probability information, at least one of a volume, length, height, width, depth, diameter, or area associated with the object of interest is estimated.

20. The system of claim 18, wherein the machine learning algorithm comprises a convolutional neural network algorithm and the memory stores instructions to execute the convolutional neural network algorithm.

21. The system of claim 18, further comprising:

a probe configured to:

an ultrasound signal is transmitted to a target of interest,

receiving echo information associated with the transmitted ultrasound signals, and

forwarding the echo information to the at least one processing device,

wherein the at least one processing device is further configured to:

generating, using the machine learning algorithm, image information corresponding to an object of interest based on the echo information.

Images